论文标题
Deep-N-Cheap：一个自动搜索框架低复杂性深学习
Deep-n-Cheap: An Automated Search Framework for Low Complexity Deep Learning
论文作者
论文摘要
我们介绍Deep-N-Cheap-一个开源的汽车框架，以搜索深度学习模型。该搜索包括体系结构和培训超参数，并支持卷积神经网络和多层感知器。我们的框架是针对基准和自定义数据集进行部署的目标，因此，与仅在文献中仅涉及的搜索更有限的搜索相比，提供了更大程度的搜索空间可自定义性。我们还介绍了“搜索传输”的技术，该技术证明了我们框架对多个数据集发现的模型的概括功能。 Deep-N-Cheap包括可及用户的复杂性罚款，该罚款将绩效与培训时间或参数数量进行交易。具体而言，我们的框架导致模型提供的性能与最先进的性能相比，而与其他汽车和模型搜索框架的模型相比，训练时间少1-2个数量级。此外，这项工作还研究并开发了有关搜索过程的各种见解。特别是，我们展示了一种贪婪策略的优越性，并证明我们选择贝叶斯优化作为主要搜索方法而不是随机 /网格搜索是合理的。
We present Deep-n-Cheap -- an open-source AutoML framework to search for deep learning models. This search includes both architecture and training hyperparameters, and supports convolutional neural networks and multi-layer perceptrons. Our framework is targeted for deployment on both benchmark and custom datasets, and as a result, offers a greater degree of search space customizability as compared to a more limited search over only pre-existing models from literature. We also introduce the technique of 'search transfer', which demonstrates the generalization capabilities of the models found by our framework to multiple datasets. Deep-n-Cheap includes a user-customizable complexity penalty which trades off performance with training time or number of parameters. Specifically, our framework results in models offering performance comparable to state-of-the-art while taking 1-2 orders of magnitude less time to train than models from other AutoML and model search frameworks. Additionally, this work investigates and develops various insights regarding the search process. In particular, we show the superiority of a greedy strategy and justify our choice of Bayesian optimization as the primary search methodology over random / grid search.
